Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1356 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.6153. Min Act: -0.1700
Data Index: 4159669 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.6153. Min Act: -0.1700
Data Index: 6824665 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5840. Min Act: -0.1700
Data Index: 803479 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5527. Min Act: -0.1700
Data Index: 6790417 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5527. Min Act: -0.1700
Data Index: 7633507 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5370. Min Act: -0.1700
Data Index: 2912655 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5370. Min Act: -0.1700
Data Index: 4126453 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.5370. Min Act: -0.1700
Data Index: 3652180 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 4403559 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 8208161 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 8250346 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 8819877 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 2237689 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4901. Min Act: -0.1700
Data Index: 2377727 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4744. Min Act: -0.1700
Data Index: 3011664 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4744. Min Act: -0.1700
Data Index: 7118667 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4431. Min Act: -0.1700
Data Index: 834248 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4274. Min Act: -0.1700
Data Index: 7350861 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4274. Min Act: -0.1700
Data Index: 1097120 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6153. Min Range: -3.6153
Max Act: 3.4274. Min Act: -0.1700
Data Index: 477360 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19